andgitchang

Excuse me to follow up this issue. @chengchunhsu I noticed that the learning rate also set as 0.005 in single_gpu settings. However, don't we need to modify the learning rate...

@chengchunhsu Thanks for your suggestion. I tried to reproduce vgg16 cityscapes->foggy-cityscapes and ended up reaching AP38.7 at iteration ~6000 (AP38.3 at iteration 8000). The only difference is that the learning...

@vidit09 I didn't try the source only experiment, since the proposed GA+CA method was trained from ImageNet pretrained backbone not the source only model. Your modified trainer looks okay. Please...

@vidit09 It's trivial since both FCOS and EveryPixelMatters use maskrcnn-benchmark. You just need to repeat [this steps](https://github.com/chengchunhsu/EveryPixelMatters#dataset) to the FCOS repo, including path_catelog and the configs.

Hi @chengchunhsu , As described in subsection 3.2 of the paper that the domain label z of source and target domain is 1 and 0 correspondingly; however, I noticed that...

Possibly you should also modify self.source_layer_indexes (GraphPath) after customizing the model.

Hi @F2Wang Following up this issue, if I would like to customize human 3d pose dataset using this repo, the pose of human must also be fixed throughout filming? If...